paper-with-me

홈 › Papers

WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization

2025-08-27 · Eduardo Davalos, Yike Zhang, Namrata Srivastava, Yashvitha Thatigotla, Jorge A. Salas, Sara McFadden, Sun-Joo Cho, Amanda Goodwin, Ashwin TS, Gautam Biswas arxiv

With advancements in AI, new gaze estimation methods are exceeding state-of-the-art (SOTA) benchmarks, but their real-world application reveals a gap with commercial eye-tracking solutions. Factors like model size, inference time, and privacy often go unaddressed. Meanwhile, webcam-based eye-tracking methods lack sufficient accuracy, in particular due to head movement. To tackle these issues, we introduce We bEyeTrack, a framework that integrates lightweight SOTA gaze estimation models directly in the browser. It incorporates model-based head pose estimation and on-device few-shot learning with as few as nine calibration samples (k < 9). WebEyeTrack adapts to new users, achieving SOTA performance with an error margin of 2.32 cm on GazeCapture and real-time inference speeds of 2.4 milliseconds on an iPhone 14. Our open-source code is available at https://github.com/RedForestAi/WebEyeTrack.

📄 PDF Abstract BibTeX arXiv:2508.19544

Code (0)

등록된 구현이 없습니다.

Tasks

Head Pose EstimationFew-Shot LearningGaze Estimation

Results from the Paper

RankTaskDatasetModelMetrics
#2 Gaze Estimation GazeCapture WEBEYETRACK Euclidean Mean Error (EME): 2.32

Similar Papers 제목 키워드 기반

Scalable Behaviour Cloning on Browser Using via Skill Distillation

2026-06-30 · Kaisen Yang, Zheng Jiang, Yuzhao Peng, Houde Qian 외 arxiv

Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflows, making human browsing a highly scalab…

Anatomizing Deep Learning Inference in Web Browsers

2024-02-08 · QiPeng Wang, Shiqi Jiang, Zhenpeng Chen, Xu Cao 외

Web applications have increasingly adopted Deep Learning (DL) through in-browser inference, wherein DL inference performs directly within Web browsers. The actual performance of in-browser inference and its impacts on th…

CPUDeep LearningGPU

Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations

2023-09-16 · Fucheng Jia, Shiqi Jiang, Ting Cao, Wei Cui 외

Web is increasingly becoming the primary platform to deliver AI services onto edge devices, making in-browser deep learning (DL) inference more prominent. Nevertheless, the heterogeneity of edge devices, combined with th…

Lightweight Real-time Makeup Try-on in Mobile Browsers with Tiny CNN Models for Facial Tracking

2019-06-05 · TianXing Li, Zhi Yu, Edmund Phung, Brendan Duke 외

Recent works on convolutional neural networks (CNNs) for facial alignment have demonstrated unprecedented accuracy on a variety of large, publicly available datasets. However, the developed models are often both cumberso…

Efficient Pose Tracking from Natural Features in Standard Web Browsers

2018-04-23 · Fabian Göttl, Philipp Gagel, Jens Grubert

Computer Vision-based natural feature tracking is at the core of modern Augmented Reality applications. Still, Web-based Augmented Reality typically relies on location-based sensing (using GPS and orientation sensors) or…

Pose EstimationPose Tracking